AI agents use ghost_create_post to create or update resources in Ghost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghost environment.
This tool creates/adds new data (blog posts) to a Ghost blog, which is a reversible modification. It does not delete, destroy, execute arbitrary code, or move funds. While it modifies published content on a public platform (raising severity above low), the action itself is reversible—posts can be edited or deleted afterward.
From the tool's definition Tool description states "Create a new Ghost post from markdown content" — the verb "create" and action of adding new content indicates a Write operation that modifies blog state reversibly.
Attacks that exploit this kind of access
Create a new Ghost post from markdown content. It is categorised as a Write tool in the Ghost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghost MCP server in PolicyLayer and add a rule for ghost_create_post: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ghost. Nothing to install.
ghost_create_post is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ghost_create_post rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ghost_create_post. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ghost_create_post is provided by the Ghost MCP server (uppinote20/ghost-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →